Search results for: graph convolutional networks (GCNs)
2225 Optimizing Production Yield Through Process Parameter Tuning Using Deep Learning Models: A Case Study in Precision Manufacturing
Authors: Tolulope Aremu
Abstract:
This paper is based on the idea of using deep learning methodology for optimizing production yield by tuning a few key process parameters in a manufacturing environment. The study was explicitly on how to maximize production yield and minimize operational costs by utilizing advanced neural network models, specifically Long Short-Term Memory and Convolutional Neural Networks. These models were implemented using Python-based frameworks—TensorFlow and Keras. The targets of the research are the precision molding processes in which temperature ranges between 150°C and 220°C, the pressure ranges between 5 and 15 bar, and the material flow rate ranges between 10 and 50 kg/h, which are critical parameters that have a great effect on yield. A dataset of 1 million production cycles has been considered for five continuous years, where detailed logs are present showing the exact setting of parameters and yield output. The LSTM model would model time-dependent trends in production data, while CNN analyzed the spatial correlations between parameters. Models are designed in a supervised learning manner. For the model's loss, an MSE loss function is used, optimized through the Adam optimizer. After running a total of 100 training epochs, 95% accuracy was achieved by the models recommending optimal parameter configurations. Results indicated that with the use of RSM and DOE traditional methods, there was an increase in production yield of 12%. Besides, the error margin was reduced by 8%, hence consistent quality products from the deep learning models. The monetary value was annually around $2.5 million, the cost saved from material waste, energy consumption, and equipment wear resulting from the implementation of optimized process parameters. This system was deployed in an industrial production environment with the help of a hybrid cloud system: Microsoft Azure, for data storage, and the training and deployment of their models were performed on Google Cloud AI. The functionality of real-time monitoring of the process and automatic tuning of parameters depends on cloud infrastructure. To put it into perspective, deep learning models, especially those employing LSTM and CNN, optimize the production yield by fine-tuning process parameters. Future research will consider reinforcement learning with a view to achieving further enhancement of system autonomy and scalability across various manufacturing sectors.Keywords: production yield optimization, deep learning, tuning of process parameters, LSTM, CNN, precision manufacturing, TensorFlow, Keras, cloud infrastructure, cost saving
Procedia PDF Downloads 292224 Use of Multivariate Statistical Techniques for Water Quality Monitoring Network Assessment, Case of Study: Jequetepeque River Basin
Authors: Jose Flores, Nadia Gamboa
Abstract:
A proper water quality management requires the establishment of a monitoring network. Therefore, evaluation of the efficiency of water quality monitoring networks is needed to ensure high-quality data collection of critical quality chemical parameters. Unfortunately, in some Latin American countries water quality monitoring programs are not sustainable in terms of recording historical data or environmentally representative sites wasting time, money and valuable information. In this study, multivariate statistical techniques, such as principal components analysis (PCA) and hierarchical cluster analysis (HCA), are applied for identifying the most significant monitoring sites as well as critical water quality parameters in the monitoring network of the Jequetepeque River basin, in northern Peru. The Jequetepeque River basin, like others in Peru, shows socio-environmental conflicts due to economical activities developed in this area. Water pollution by trace elements in the upper part of the basin is mainly related with mining activity, and agricultural land lost due to salinization is caused by the extensive use of groundwater in the lower part of the basin. Since the 1980s, the water quality in the basin has been non-continuously assessed by public and private organizations, and recently the National Water Authority had established permanent water quality networks in 45 basins in Peru. Despite many countries use multivariate statistical techniques for assessing water quality monitoring networks, those instruments have never been applied for that purpose in Peru. For this reason, the main contribution of this study is to demonstrate that application of the multivariate statistical techniques could serve as an instrument that allows the optimization of monitoring networks using least number of monitoring sites as well as the most significant water quality parameters, which would reduce costs concerns and improve the water quality management in Peru. Main socio-economical activities developed and the principal stakeholders related to the water management in the basin are also identified. Finally, water quality management programs will also be discussed in terms of their efficiency and sustainability.Keywords: PCA, HCA, Jequetepeque, multivariate statistical
Procedia PDF Downloads 3552223 Towards a Balancing Medical Database by Using the Least Mean Square Algorithm
Authors: Kamel Belammi, Houria Fatrim
Abstract:
imbalanced data set, a problem often found in real world application, can cause seriously negative effect on classification performance of machine learning algorithms. There have been many attempts at dealing with classification of imbalanced data sets. In medical diagnosis classification, we often face the imbalanced number of data samples between the classes in which there are not enough samples in rare classes. In this paper, we proposed a learning method based on a cost sensitive extension of Least Mean Square (LMS) algorithm that penalizes errors of different samples with different weight and some rules of thumb to determine those weights. After the balancing phase, we applythe different classifiers (support vector machine (SVM), k- nearest neighbor (KNN) and multilayer neuronal networks (MNN)) for balanced data set. We have also compared the obtained results before and after balancing method.Keywords: multilayer neural networks, k- nearest neighbor, support vector machine, imbalanced medical data, least mean square algorithm, diabetes
Procedia PDF Downloads 5322222 Emotion-Convolutional Neural Network for Perceiving Stress from Audio Signals: A Brain Chemistry Approach
Authors: Anup Anand Deshmukh, Catherine Soladie, Renaud Seguier
Abstract:
Emotion plays a key role in many applications like healthcare, to gather patients’ emotional behavior. Unlike typical ASR (Automated Speech Recognition) problems which focus on 'what was said', it is equally important to understand 'how it was said.' There are certain emotions which are given more importance due to their effectiveness in understanding human feelings. In this paper, we propose an approach that models human stress from audio signals. The research challenge in speech emotion detection is finding the appropriate set of acoustic features corresponding to an emotion. Another difficulty lies in defining the very meaning of emotion and being able to categorize it in a precise manner. Supervised Machine Learning models, including state of the art Deep Learning classification methods, rely on the availability of clean and labelled data. One of the problems in affective computation is the limited amount of annotated data. The existing labelled emotions datasets are highly subjective to the perception of the annotator. We address the first issue of feature selection by exploiting the use of traditional MFCC (Mel-Frequency Cepstral Coefficients) features in Convolutional Neural Network. Our proposed Emo-CNN (Emotion-CNN) architecture treats speech representations in a manner similar to how CNN’s treat images in a vision problem. Our experiments show that Emo-CNN consistently and significantly outperforms the popular existing methods over multiple datasets. It achieves 90.2% categorical accuracy on the Emo-DB dataset. We claim that Emo-CNN is robust to speaker variations and environmental distortions. The proposed approach achieves 85.5% speaker-dependant categorical accuracy for SAVEE (Surrey Audio-Visual Expressed Emotion) dataset, beating the existing CNN based approach by 10.2%. To tackle the second problem of subjectivity in stress labels, we use Lovheim’s cube, which is a 3-dimensional projection of emotions. Monoamine neurotransmitters are a type of chemical messengers in the brain that transmits signals on perceiving emotions. The cube aims at explaining the relationship between these neurotransmitters and the positions of emotions in 3D space. The learnt emotion representations from the Emo-CNN are mapped to the cube using three component PCA (Principal Component Analysis) which is then used to model human stress. This proposed approach not only circumvents the need for labelled stress data but also complies with the psychological theory of emotions given by Lovheim’s cube. We believe that this work is the first step towards creating a connection between Artificial Intelligence and the chemistry of human emotions.Keywords: deep learning, brain chemistry, emotion perception, Lovheim's cube
Procedia PDF Downloads 1542221 Refactoring Object Oriented Software through Community Detection Using Evolutionary Computation
Authors: R. Nagarani
Abstract:
An intrinsic property of software in a real-world environment is its need to evolve, which is usually accompanied by the increase of software complexity and deterioration of software quality, making software maintenance a tough problem. Refactoring is regarded as an effective way to address this problem. Many refactoring approaches at the method and class level have been proposed. But the extent of research on software refactoring at the package level is less. This work presents a novel approach to refactor the package structures of object oriented software using genetic algorithm based community detection. It uses software networks to represent classes and their dependencies. It uses a constrained community detection algorithm to obtain the optimized community structures in software networks, which also correspond to the optimized package structures. It finally provides a list of classes as refactoring candidates by comparing the optimized package structures with the real package structures.Keywords: community detection, complex network, genetic algorithm, package, refactoring
Procedia PDF Downloads 4182220 Spectrogram Pre-Processing to Improve Isotopic Identification to Discriminate Gamma and Neutrons Sources
Authors: Mustafa Alhamdi
Abstract:
Industrial application to classify gamma rays and neutron events is investigated in this study using deep machine learning. The identification using a convolutional neural network and recursive neural network showed a significant improvement in predication accuracy in a variety of applications. The ability to identify the isotope type and activity from spectral information depends on feature extraction methods, followed by classification. The features extracted from the spectrum profiles try to find patterns and relationships to present the actual spectrum energy in low dimensional space. Increasing the level of separation between classes in feature space improves the possibility to enhance classification accuracy. The nonlinear nature to extract features by neural network contains a variety of transformation and mathematical optimization, while principal component analysis depends on linear transformations to extract features and subsequently improve the classification accuracy. In this paper, the isotope spectrum information has been preprocessed by finding the frequencies components relative to time and using them as a training dataset. Fourier transform implementation to extract frequencies component has been optimized by a suitable windowing function. Training and validation samples of different isotope profiles interacted with CdTe crystal have been simulated using Geant4. The readout electronic noise has been simulated by optimizing the mean and variance of normal distribution. Ensemble learning by combing voting of many models managed to improve the classification accuracy of neural networks. The ability to discriminate gamma and neutron events in a single predication approach using deep machine learning has shown high accuracy using deep learning. The paper findings show the ability to improve the classification accuracy by applying the spectrogram preprocessing stage to the gamma and neutron spectrums of different isotopes. Tuning deep machine learning models by hyperparameter optimization of neural network models enhanced the separation in the latent space and provided the ability to extend the number of detected isotopes in the training database. Ensemble learning contributed significantly to improve the final prediction.Keywords: machine learning, nuclear physics, Monte Carlo simulation, noise estimation, feature extraction, classification
Procedia PDF Downloads 1502219 A Context-Centric Chatbot for Cryptocurrency Using the Bidirectional Encoder Representations from Transformers Neural Networks
Authors: Qitao Xie, Qingquan Zhang, Xiaofei Zhang, Di Tian, Ruixuan Wen, Ting Zhu, Ping Yi, Xin Li
Abstract:
Inspired by the recent movement of digital currency, we are building a question answering system concerning the subject of cryptocurrency using Bidirectional Encoder Representations from Transformers (BERT). The motivation behind this work is to properly assist digital currency investors by directing them to the corresponding knowledge bases that can offer them help and increase the querying speed. BERT, one of newest language models in natural language processing, was investigated to improve the quality of generated responses. We studied different combinations of hyperparameters of the BERT model to obtain the best fit responses. Further, we created an intelligent chatbot for cryptocurrency using BERT. A chatbot using BERT shows great potential for the further advancement of a cryptocurrency market tool. We show that the BERT neural networks generalize well to other tasks by applying it successfully to cryptocurrency.Keywords: bidirectional encoder representations from transformers, BERT, chatbot, cryptocurrency, deep learning
Procedia PDF Downloads 1472218 Morphological Features Fusion for Identifying INBREAST-Database Masses Using Neural Networks and Support Vector Machines
Authors: Nadia el Atlas, Mohammed el Aroussi, Mohammed Wahbi
Abstract:
In this paper a novel technique of mass characterization based on robust features-fusion is presented. The proposed method consists of mainly four stages: (a) the first phase involves segmenting the masses using edge information’s. (b) The second phase is to calculate and fuse the most relevant morphological features. (c) The last phase is the classification step which allows us to classify the images into benign and malignant masses. In this step we have implemented Support Vectors Machines (SVM) and Artificial Neural Networks (ANN), which were evaluated with the following performance criteria: confusion matrix, accuracy, sensitivity, specificity, receiver operating characteristic ROC, and error histogram. The effectiveness of this new approach was evaluated by a recently developed database: INBREAST database. The fusion of the most appropriate morphological features provided very good results. The SVM gives accuracy to within 64.3%. Whereas the ANN classifier gives better results with an accuracy of 97.5%.Keywords: breast cancer, mammography, CAD system, features, fusion
Procedia PDF Downloads 5992217 Urban Growth Prediction Using Artificial Neural Networks in Athens, Greece
Authors: Dimitrios Triantakonstantis, Demetris Stathakis
Abstract:
Urban areas have been expanded throughout the globe. Monitoring and modeling urban growth have become a necessity for a sustainable urban planning and decision making. Urban prediction models are important tools for analyzing the causes and consequences of urban land use dynamics. The objective of this research paper is to analyze and model the urban change, which has been occurred from 1990 to 2000 using CORINE land cover maps. The model was developed using drivers of urban changes (such as road distance, slope, etc.) under an Artificial Neural Network modeling approach. Validation was achieved using a prediction map for 2006 which was compared with a real map of Urban Atlas of 2006. The accuracy produced a Kappa index of agreement of 0,639 and a value of Cramer's V of 0,648. These encouraging results indicate the importance of the developed urban growth prediction model which using a set of available common biophysical drivers could serve as a management tool for the assessment of urban change.Keywords: artificial neural networks, CORINE, urban atlas, urban growth prediction
Procedia PDF Downloads 5282216 Introduction to Transversal Pendant Domination in Graphs
Authors: Nayaka S.R., Putta Swamy, Purushothama S.
Abstract:
Let G=(V, E) be a graph. A dominating set S in G is a pendant dominating set if < S > contains a pendant vertex. A pendant dominating set of G which intersects every minimum pendant dominating set in G is called a transversal pendant dominating set. The minimum cardinality of a transversal pendant dominating set is called the transversal pendant domination number of G, denoted by γ_tp(G). In this paper, we begin to study this parameter. We calculate γ_tp(G) for some families of graphs. Furthermore, some bounds and relations with other domination parameters are obtained for γ_tp(G).Keywords: dominating set, pendant dominating set, pendant domination number, transversal pendant dominating set, transversal pendant domination number
Procedia PDF Downloads 1822215 Behaviour of an RC Circuit near Extreme Point
Authors: Tribhuvan N. Soorya
Abstract:
Charging and discharging of a capacitor through a resistor can be shown as exponential curve. Theoretically, it takes infinite time to fully charge or discharge a capacitor. The flow of charge is due to electrons having finite and fixed value of charge. If we carefully examine the charging and discharging process after several time constants, the points on q vs t graph become discrete and curve become discontinuous. Moreover for all practical purposes capacitor with charge (q0-e) can be taken as fully charged, as it introduces an error less than one part per million. Similar is the case for discharge of a capacitor, where the capacitor with the last electron (charge e) can be taken as fully discharged. With this, we can estimate the finite value of time for fully charging and discharging a capacitor.Keywords: charging, discharging, RC Circuit, capacitor
Procedia PDF Downloads 4432214 Secure Transmission Scheme in Device-to-Device Multicast Communications
Authors: Bangwon Seo
Abstract:
In this paper, we consider multicast device-to-device (D2D) direct communication systems in cellular networks. In multicast D2D communications, nearby mobile devices exchanges, their data directly without going through a base station and a D2D transmitter send its data to multiple D2D receivers that compose of D2D multicast group. We consider wiretap channel where there is an eavesdropper that attempts to overhear the transmitted data of the D2D transmitter. In this paper, we propose a secure transmission scheme in D2D multicast communications in cellular networks. In order to prevent the eavesdropper from overhearing the transmitted data of the D2D transmitter, a precoding vector is employed at the D2D transmitter in the proposed scheme. We perform computer simulations to evaluate the performance of the proposed scheme. Through the simulation, we show that the secrecy rate performance can be improved by selecting an appropriate precoding vector.Keywords: device-to-device communications, wiretap channel, secure transmission, precoding
Procedia PDF Downloads 2912213 Robot Movement Using the Trust Region Policy Optimization
Authors: Romisaa Ali
Abstract:
The Policy Gradient approach is one of the deep reinforcement learning families that combines deep neural networks (DNN) with reinforcement learning RL to discover the optimum of the control problem through experience gained from the interaction between the robot and its surroundings. In contrast to earlier policy gradient algorithms, which were unable to handle these two types of error because of over-or under-estimation introduced by the deep neural network model, this article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.Keywords: deep neural networks, deep reinforcement learning, proximal policy optimization, state-of-the-art, trust region policy optimization
Procedia PDF Downloads 1692212 Wireless Sensor Anomaly Detection Using Soft Computing
Authors: Mouhammd Alkasassbeh, Alaa Lasasmeh
Abstract:
We live in an era of rapid development as a result of significant scientific growth. Like other technologies, wireless sensor networks (WSNs) are playing one of the main roles. Based on WSNs, ZigBee adds many features to devices, such as minimum cost and power consumption, and increasing the range and connect ability of sensor nodes. ZigBee technology has come to be used in various fields, including science, engineering, and networks, and even in medicinal aspects of intelligence building. In this work, we generated two main datasets, the first being based on tree topology and the second on star topology. The datasets were evaluated by three machine learning (ML) algorithms: J48, meta.j48 and multilayer perceptron (MLP). Each topology was classified into normal and abnormal (attack) network traffic. The dataset used in our work contained simulated data from network simulation 2 (NS2). In each database, the Bayesian network meta.j48 classifier achieved the highest accuracy level among other classifiers, of 99.7% and 99.2% respectively.Keywords: IDS, Machine learning, WSN, ZigBee technology
Procedia PDF Downloads 5432211 DeClEx-Processing Pipeline for Tumor Classification
Authors: Gaurav Shinde, Sai Charan Gongiguntla, Prajwal Shirur, Ahmed Hambaba
Abstract:
Health issues are significantly increasing, putting a substantial strain on healthcare services. This has accelerated the integration of machine learning in healthcare, particularly following the COVID-19 pandemic. The utilization of machine learning in healthcare has grown significantly. We introduce DeClEx, a pipeline that ensures that data mirrors real-world settings by incorporating Gaussian noise and blur and employing autoencoders to learn intermediate feature representations. Subsequently, our convolutional neural network, paired with spatial attention, provides comparable accuracy to state-of-the-art pre-trained models while achieving a threefold improvement in training speed. Furthermore, we provide interpretable results using explainable AI techniques. We integrate denoising and deblurring, classification, and explainability in a single pipeline called DeClEx.Keywords: machine learning, healthcare, classification, explainability
Procedia PDF Downloads 552210 Reliability-Based Maintenance Management Methodology to Minimise Life Cycle Cost of Water Supply Networks
Authors: Mojtaba Mahmoodian, Joshua Phelan, Mehdi Shahparvari
Abstract:
With a large percentage of countries’ total infrastructure expenditure attributed to water network maintenance, it is essential to optimise maintenance strategies to rehabilitate or replace underground pipes before failure occurs. The aim of this paper is to provide water utility managers with a maintenance management approach for underground water pipes, subject to external loading and material corrosion, to give the lowest life cycle cost over a predetermined time period. This reliability-based maintenance management methodology details the optimal years for intervention, the ideal number of maintenance activities to perform before replacement and specifies feasible renewal options and intervention prioritisation to minimise the life cycle cost. The study was then extended to include feasible renewal methods by determining the structural condition index and potential for soil loss, then obtaining the failure impact rating to assist in prioritising pipe replacement. A case study on optimisation of maintenance plans for the Melbourne water pipe network is considered in this paper to evaluate the practicality of the proposed methodology. The results confirm that the suggested methodology can provide water utility managers with a reliable systematic approach to determining optimum maintenance plans for pipe networks.Keywords: water pipe networks, maintenance management, reliability analysis, optimum maintenance plan
Procedia PDF Downloads 1552209 On Virtual Coordination Protocol towards 5G Interference Mitigation: Modelling and Performance Analysis
Authors: Bohli Afef
Abstract:
The fifth-generation (5G) wireless systems is featured by extreme densities of cell stations to overcome the higher future demand. Hence, interference management is a crucial challenge in 5G ultra-dense cellular networks. In contrast to the classical inter-cell interference coordination approach, which is no longer fit for the high density of cell-tiers, this paper proposes a novel virtual coordination based on the dynamic common cognitive monitor channel protocol to deal with the inter-cell interference issue. A tractable and flexible model for the coverage probability of a typical user is developed through the use of the stochastic geometry model. The analyses of the performance of the suggested protocol are illustrated both analytically and numerically in terms of coverage probability.Keywords: ultra dense heterogeneous networks, dynamic common channel protocol, cognitive radio, stochastic geometry, coverage probability
Procedia PDF Downloads 3252208 Evaluation of Routing Protocols in Mobile Adhoc Networks
Authors: Anu Malhotra
Abstract:
An Ad-hoc network is one that is an autonomous, self configuring network made up of mobile nodes connected via wireless links. Ad-hoc networks often consist of nodes, mobile hosts (MH) or mobile stations (MS, also serving as routers) connected by wireless links. Different routing protocols are used for data transmission in between the nodes in an adhoc network. In this paper two protocols (OLSR and AODV) are analyzed on the basis of two parameters i.e. time delay and throughput with different data rates. On the basis of these analysis, we observed that with same data rate, AODV protocol is having more time delay than the OLSR protocol whereas throughput for the OLSR protocol is less compared to the AODV protocol.Keywords: routing adhoc, mobile hosts, mobile stations, OLSR protocol, AODV protocol
Procedia PDF Downloads 5052207 Artificial Neural Networks Based Calibration Approach for Six-Port Receiver
Authors: Nadia Chagtmi, Nejla Rejab, Noureddine Boulejfen
Abstract:
This paper presents a calibration approach based on artificial neural networks (ANN) to determine the envelop signal (I+jQ) of a six-port based receiver (SPR). The memory effects called also dynamic behavior and the nonlinearity brought by diode based power detector have been taken into consideration by the ANN. Experimental set-up has been performed to validate the efficiency of this method. The efficiency of this approach has been confirmed by the obtained results in terms of waveforms. Moreover, the obtained error vector magnitude (EVM) and the mean absolute error (MAE) have been calculated in order to confirm and to test the ANN’s performance to achieve I/Q recovery using the output voltage detected by the power based detector. The baseband signal has been recovered using ANN with EVMs no higher than 1 % and an MAE no higher than 17, 26 for the SPR excited different type of signals such QAM (quadrature amplitude modulation) and LTE (Long Term Evolution).Keywords: six-port based receiver; calibration, nonlinearity, memory effect, artificial neural network
Procedia PDF Downloads 762206 Avoiding Packet Drop for Improved through Put in the Multi-Hop Wireless N/W
Authors: Manish Kumar Rajak, Sanjay Gupta
Abstract:
Mobile ad hoc networks (MANETs) are infrastructure less and intercommunicate using single-hop and multi-hop paths. Network based congestion avoidance which involves managing the queues in the network devices is an integral part of any network. QoS: A set of service requirements that are met by the network while transferring a packet stream from a source to a destination. Especially in MANETs, packet loss results in increased overheads. This paper presents a new algorithm to avoid congestion using one or more queue on nodes and corresponding flow rate decided in advance for each node. When any node attains an initial value of queue then it sends this status to its downstream nodes which in turn uses the pre-decided flow rate of packet transfer to its upstream nodes. The flow rate on each node is adjusted according to the status received from its upstream nodes. This proposed algorithm uses the existing infrastructure to inform to other nodes about its current queue status.Keywords: mesh networks, MANET, packet count, threshold, throughput
Procedia PDF Downloads 4742205 Application of an Artificial Neural Network to Determine the Risk of Malignant Tumors from the Images Resulting from the Asymmetry of Internal and External Thermograms of the Mammary Glands
Authors: Amdy Moustapha Drame, Ilya V. Germashev, E. A. Markushevskaya
Abstract:
Among the main problems of medicine is breast cancer, from which a significant number of women around the world are constantly dying. Therefore, the detection of malignant breast tumors is an urgent task. For many years, various technologies for detecting these tumors have been used, in particular, in thermal imaging in order to determine different levels of breast cancer development. These periodic screening methods are a diagnostic tool for women and may have become an alternative to older methods such as mammography. This article proposes a model for the identification of malignant neoplasms of the mammary glands by the asymmetry of internal and external thermal imaging fields.Keywords: asymmetry, breast cancer, tumors, deep learning, thermogram, convolutional transformation, classification
Procedia PDF Downloads 602204 Neuronal Networks for the Study of the Effects of Cosmic Rays on Climate Variations
Authors: Jossitt Williams Vargas Cruz, Aura Jazmín Pérez Ríos
Abstract:
The variations of solar dynamics have become a relevant topic of study due to the effects of climate changes generated on the earth. One of the most disconcerting aspects is the variability that the sun has on the climate is the role played by sunspots (extra-atmospheric variable) in the modulation of the Cosmic Rays CR (extra-atmospheric variable). CRs influence the earth's climate by affecting cloud formation (atmospheric variable), and solar cycle influence is associated with the presence of solar storms, and the magnetic activity is greater, resulting in less CR entering the earth's atmosphere. The different methods of climate prediction in Colombia do not take into account the extra-atmospheric variables. Therefore, correlations between atmospheric and extra-atmospheric variables were studied in order to implement a Python code based on neural networks to make the prediction of the extra-atmospheric variable with the highest correlation.Keywords: correlations, cosmic rays, sun, sunspots and variations.
Procedia PDF Downloads 732203 Estimating Cyclone Intensity Using INSAT-3D IR Images Based on Convolution Neural Network Model
Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi
Abstract:
Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models
Procedia PDF Downloads 1262202 Persistent Homology of Convection Cycles in Network Flows
Authors: Minh Quang Le, Dane Taylor
Abstract:
Convection is a well-studied topic in fluid dynamics, yet it is less understood in the context of networks flows. Here, we incorporate techniques from topological data analysis (namely, persistent homology) to automate the detection and characterization of convective/cyclic/chiral flows over networks, particularly those that arise for irreversible Markov chains (MCs). As two applications, we study convection cycles arising under the PageRank algorithm, and we investigate chiral edges flows for a stochastic model of a bi-monomer's configuration dynamics. Our experiments highlight how system parameters---e.g., the teleportation rate for PageRank and the transition rates of external and internal state changes for a monomer---can act as homology regularizers of convection, which we summarize with persistence barcodes and homological bifurcation diagrams. Our approach establishes a new connection between the study of convection cycles and homology, the branch of mathematics that formally studies cycles, which has diverse potential applications throughout the sciences and engineering.Keywords: homology, persistent homolgy, markov chains, convection cycles, filtration
Procedia PDF Downloads 1362201 Prediction of Formation Pressure Using Artificial Intelligence Techniques
Authors: Abdulmalek Ahmed
Abstract:
Formation pressure is the main function that affects drilling operation economically and efficiently. Knowing the pore pressure and the parameters that affect it will help to reduce the cost of drilling process. Many empirical models reported in the literature were used to calculate the formation pressure based on different parameters. Some of these models used only drilling parameters to estimate pore pressure. Other models predicted the formation pressure based on log data. All of these models required different trends such as normal or abnormal to predict the pore pressure. Few researchers applied artificial intelligence (AI) techniques to predict the formation pressure by only one method or a maximum of two methods of AI. The objective of this research is to predict the pore pressure based on both drilling parameters and log data namely; weight on bit, rotary speed, rate of penetration, mud weight, bulk density, porosity and delta sonic time. A real field data is used to predict the formation pressure using five different artificial intelligence (AI) methods such as; artificial neural networks (ANN), radial basis function (RBF), fuzzy logic (FL), support vector machine (SVM) and functional networks (FN). All AI tools were compared with different empirical models. AI methods estimated the formation pressure by a high accuracy (high correlation coefficient and low average absolute percentage error) and outperformed all previous. The advantage of the new technique is its simplicity, which represented from its estimation of pore pressure without the need of different trends as compared to other models which require a two different trend (normal or abnormal pressure). Moreover, by comparing the AI tools with each other, the results indicate that SVM has the advantage of pore pressure prediction by its fast processing speed and high performance (a high correlation coefficient of 0.997 and a low average absolute percentage error of 0.14%). In the end, a new empirical correlation for formation pressure was developed using ANN method that can estimate pore pressure with a high precision (correlation coefficient of 0.998 and average absolute percentage error of 0.17%).Keywords: Artificial Intelligence (AI), Formation pressure, Artificial Neural Networks (ANN), Fuzzy Logic (FL), Support Vector Machine (SVM), Functional Networks (FN), Radial Basis Function (RBF)
Procedia PDF Downloads 1492200 Exploring Long-Term Care Support Networks and Social Capital for Family Caregivers
Authors: Liu Yi-Hui, Chiu Fan-Yun, Lin Yu Fang, Jhang Yu Cih, He You Jing
Abstract:
The demand for care support has been rising with the aging of society and the advancement of medical science and technology. To meet rising demand, the Taiwanese government promoted the “Long Term Care Ten-Year Plan 2.0” in 2017. However, this policy and its related services failed to be fully implemented because of the ignorance of the public, and their lack of desire, fear, or discomfort in using them, which is a major obstacle to the promotion of long-term care services. Given the above context, this research objectives included the following: (1) to understand the current situation and predicament of family caregivers; (2) to reveal the actual use and assistance of government’s long-term care resources for family caregivers; and (3) to explore the support and impact of social capital on family caregivers. A semi-structured in-depth interview with five family caregivers to understand long-term care networks and social capital for family caregivers.Keywords: family caregivers, long-term care, social capital
Procedia PDF Downloads 1572199 Opinion Mining and Sentiment Analysis on DEFT
Authors: Najiba Ouled Omar, Azza Harbaoui, Henda Ben Ghezala
Abstract:
Current research practices sentiment analysis with a focus on social networks, DEfi Fouille de Texte (DEFT) (Text Mining Challenge) evaluation campaign focuses on opinion mining and sentiment analysis on social networks, especially social network Twitter. It aims to confront the systems produced by several teams from public and private research laboratories. DEFT offers participants the opportunity to work on regularly renewed themes and proposes to work on opinion mining in several editions. The purpose of this article is to scrutinize and analyze the works relating to opinions mining and sentiment analysis in the Twitter social network realized by DEFT. It examines the tasks proposed by the organizers of the challenge and the methods used by the participants.Keywords: opinion mining, sentiment analysis, emotion, polarity, annotation, OSEE, figurative language, DEFT, Twitter, Tweet
Procedia PDF Downloads 1382198 KPI and Tool for the Evaluation of Competency in Warehouse Management for Furniture Business
Authors: Kritchakhris Na-Wattanaprasert
Abstract:
The objective of this research is to design and develop a prototype of a key performance indicator system this is suitable for warehouse management in a case study and use requirement. In this study, we design a prototype of key performance indicator system (KPI) for warehouse case study of furniture business by methodology in step of identify scope of the research and study related papers, gather necessary data and users requirement, develop key performance indicator base on balance scorecard, design pro and database for key performance indicator, coding the program and set relationship of database and finally testing and debugging each module. This study use Balance Scorecard (BSC) for selecting and grouping key performance indicator. The system developed by using Microsoft SQL Server 2010 is used to create the system database. In regard to visual-programming language, Microsoft Visual C# 2010 is chosen as the graphic user interface development tool. This system consists of six main menus: menu login, menu main data, menu financial perspective, menu customer perspective, menu internal, and menu learning and growth perspective. Each menu consists of key performance indicator form. Each form contains a data import section, a data input section, a data searches – edit section, and a report section. The system generates outputs in 5 main reports, the KPI detail reports, KPI summary report, KPI graph report, benchmarking summary report and benchmarking graph report. The user will select the condition of the report and period time. As the system has been developed and tested, discovers that it is one of the ways to judging the extent to warehouse objectives had been achieved. Moreover, it encourages the warehouse functional proceed with more efficiency. In order to be useful propose for other industries, can adjust this system appropriately. To increase the usefulness of the key performance indicator system, the recommendations for further development are as follows: -The warehouse should review the target value and set the better suitable target periodically under the situation fluctuated in the future. -The warehouse should review the key performance indicators and set the better suitable key performance indicators periodically under the situation fluctuated in the future for increasing competitiveness and take advantage of new opportunities.Keywords: key performance indicator, warehouse management, warehouse operation, logistics management
Procedia PDF Downloads 4312197 A Topology-Based Dynamic Repair Strategy for Enhancing Urban Road Network Resilience under Flooding
Authors: Xuhui Lin, Qiuchen Lu, Yi An, Tao Yang
Abstract:
As global climate change intensifies, extreme weather events such as floods increasingly threaten urban infrastructure, making the vulnerability of urban road networks a pressing issue. Existing static repair strategies fail to adapt to the rapid changes in road network conditions during flood events, leading to inefficient resource allocation and suboptimal recovery. The main research gap lies in the lack of repair strategies that consider both the dynamic characteristics of networks and the progression of flood propagation. This paper proposes a topology-based dynamic repair strategy that adjusts repair priorities based on real-time changes in flood propagation and traffic demand. Specifically, a novel method is developed to assess and enhance the resilience of urban road networks during flood events. The method combines road network topological analysis, flood propagation modelling, and traffic flow simulation, introducing a local importance metric to dynamically evaluate the significance of road segments across different spatial and temporal scales. Using London's road network and rainfall data as a case study, the effectiveness of this dynamic strategy is compared to traditional and Transport for London (TFL) strategies. The most significant highlight of the research is that the dynamic strategy substantially reduced the number of stranded vehicles across different traffic demand periods, improving efficiency by up to 35.2%. The advantage of this method lies in its ability to adapt in real-time to changes in network conditions, enabling more precise resource allocation and more efficient repair processes. This dynamic strategy offers significant value to urban planners, traffic management departments, and emergency response teams, helping them better respond to extreme weather events like floods, enhance overall urban resilience, and reduce economic losses and social impacts.Keywords: Urban resilience, road networks, flood response, dynamic repair strategy, topological analysis
Procedia PDF Downloads 352196 The Fibonacci Network: A Simple Alternative for Positional Encoding
Authors: Yair Bleiberg, Michael Werman
Abstract:
Coordinate-based Multi-Layer Perceptrons (MLPs) are known to have difficulty reconstructing high frequencies of the training data. A common solution to this problem is Positional Encoding (PE), which has become quite popular. However, PE has drawbacks. It has high-frequency artifacts and adds another hyper hyperparameter, just like batch normalization and dropout do. We believe that under certain circumstances, PE is not necessary, and a smarter construction of the network architecture together with a smart training method is sufficient to achieve similar results. In this paper, we show that very simple MLPs can quite easily output a frequency when given input of the half-frequency and quarter-frequency. Using this, we design a network architecture in blocks, where the input to each block is the output of the two previous blocks along with the original input. We call this a Fibonacci Network. By training each block on the corresponding frequencies of the signal, we show that Fibonacci Networks can reconstruct arbitrarily high frequencies.Keywords: neural networks, positional encoding, high frequency intepolation, fully connected
Procedia PDF Downloads 98